Compress tool outputs, logs, files, and RAG chunks before they reach the LLM. 20% fewer tokens for coding agents, 60-95% fewer tokens for JSON, same answers. Library, proxy, MCP server.
Python agentaianthropicclaude-codecompressioncontext-engineeringcontext-windowcursorfastapilangchainllmmcpopenaiprompt-engineeringproxypythonragtoken-optimizationtokenstypescript
docs: clarify proxy-backed MCP setup
Sven Meyer59dc4a508ae8
diff --git a/docs/content/docs/mcp.mdx b/docs/content/docs/mcp.mdxindex 018da9546..0ba68d006 100644--- a/docs/content/docs/mcp.mdx+++ b/docs/content/docs/mcp.mdx@@ -117,6 +117,43 @@ headroom mcp uninstallheadroom mcp serve --debug```+## MCP host configuration++For MCP hosts that let you configure a local stdio server, point them at `headroom mcp serve`. If you also run the proxy, pass the proxy URL explicitly so retrieval and stats come from the intended proxy instance.++```json+{+ "mcpServers": {+ "headroom": {+ "type": "stdio",+ "command": "headroom",+ "args": ["mcp", "serve", "--proxy-url", "http://127.0.0.1:8787"]+ }+ }+}+```++For multiple proxy instances, register one stdio MCP server per proxy URL:++```json+{+ "mcpServers": {+ "headroom": {+ "type": "stdio",+ "command": "headroom",+ "args": ["mcp", "serve", "--proxy-url", "http://127.0.0.1:8787"]+ },+ "headroom-azure": {+ "type": "stdio",+ "command": "headroom",+ "args": ["mcp", "serve", "--proxy-url", "http://127.0.0.1:8788"]+ }+ }+}+```++Do not assume that a running proxy exposes an HTTP MCP endpoint at `/mcp`. If `http://127.0.0.1:<port>/mcp` returns `404`, use the stdio configuration above.+## Cross-tool compatibility| Tool | MCP Support | Setup |